FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning

Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning is a natural alternative, yet standard federated pipelines optimize prediction quality rather than decision quality and do not account for client heterogeneity in downstream objectives or feasible sets. Heterogeneity is especially problematic for DFL methods: under heterogeneous polyhedral decision problems, small perturbations can cause discontinuous changes in optimal decisions, leading to unstable client updates and aggregation. We propose FedRSPO+, a heterogeneity-aware framework for decision-focused federated learning. Our approach is built on RSPO+, a regularized predict-then-optimize surrogate that smooths the decision map through projection, enabling stable optimization even when clients face different objectives and constraints. We show that RSPO+ upper bounds downstream decision error and regret under mild assumptions, and that FedRSPO+ has cross-client heterogeneity bounds that (i) scale with both objective and feasible-set heterogeneity, (ii) vanish at homogeneity, and (iii) do not require strong convexity. We develop an annealed and modular training procedure that is compatible with standard federated personalization and aggregation methods. We evaluate FedRSPO+ on three experimental settings: controlled synthetic knapsack instances that isolate multiple axes of heterogeneity, a shortest path DFL benchmark, and a real-world PJM energy pricing case study. Across these experiments, we compare against prediction-only federated learning and DFL frameworks under varying heterogeneity and communication budgets. Together, our results suggest that smoothing is a useful ingredient for stable collaborative decision learning and provide a first heterogeneity-aware foundation for federated DFL.